Full-scale Deeply Supervised Attention Network for Segmenting COVID-19 Lesions

TL;DR

FuDSA-Net is a novel deep learning model that effectively segments COVID-19 lung lesions in CT scans by leveraging multi-scale features and attention mechanisms, outperforming existing methods especially for complex lesion shapes.

Contribution

Introduces FuDSA-Net, a deep supervision and attention-based network that captures multi-scalar features for improved COVID-19 lesion segmentation in CT images.

Findings

FuDSA-Net outperforms state-of-the-art models in lesion segmentation accuracy.

The model effectively handles lesions with complex geometries.

Deep supervision and multi-scale attention improve segmentation robustness.

Abstract

Automated delineation of COVID-19 lesions from lung CT scans aids the diagnosis and prognosis for patients. The asymmetric shapes and positioning of the infected regions make the task extremely difficult. Capturing information at multiple scales will assist in deciphering features, at global and local levels, to encompass lesions of variable size and texture. We introduce the Full-scale Deeply Supervised Attention Network (FuDSA-Net), for efficient segmentation of corona-infected lung areas in CT images. The model considers activation responses from all levels of the encoding path, encompassing multi-scalar features acquired at different levels of the network. This helps segment target regions (lesions) of varying shape, size and contrast. Incorporation of the entire gamut of multi-scalar characteristics into the novel attention mechanism helps prioritize the selection of activation responses and locations containing useful information. Determining robust and discriminatory features along the decoder path is facilitated with deep supervision. Connections in the decoder arm are remodeled to handle the issue of vanishing gradient. As observed from the experimental results, FuDSA-Net surpasses other state-of-the-art architectures; especially, when it comes to characterizing complicated geometries of the lesions.